paper-fetch — Claude Code skill: PDF search and setup
Finds and downloads research paper PDFs from a DOI, title, or DOI list. Handy when you need to retrieve a paper from available sources.
npx skills add Agents365-ai/365-skills --skill paper-fetch -a claude-codeWhat paper-fetch does
For a DOI, the skill checks sources in sequence: Unpaywall, Semantic Scholar, arXiv, PubMed Central, then bioRxiv or medRxiv. With a title instead, it looks for a DOI through Crossref and can turn to Semantic Scholar if needed. You can also provide a file containing multiple DOIs.
Run it with python scripts/fetch.py; files go to pdfs by default, and agent output is JSON. It requires python3. Direct publisher downloads need PAPER_FETCH_INSTITUTIONAL=1; Sci-Hub fallback is enabled by default and can be turned off with PAPER_FETCH_NO_SCIHUB=1.
What it helps with
- find a paper PDF from its DOI
- resolve a paper title to a DOI and download its PDF
- fetch papers listed in a DOI file
- save retrieved papers to a chosen directory
Example prompts for the agent
- Find and download the PDF for DOI
10.1234/example. - Look up the paper titled “Example Paper Title” and save its PDF.
- Download the papers listed in
papers.txt.
How to install paper-fetch
1Skills CLI (Vercel)
npx skills add Agents365-ai/365-skills --skill paper-fetch -a claude-code2Manually: put the files in place
~/.claude/skills/paper-fetch/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/paper-fetch/
1Skills CLI (Vercel)
npx skills add Agents365-ai/365-skills --skill paper-fetch -a codex2Manually: put the files in place
.agents/skills/paper-fetch/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add Agents365-ai/365-skills --skill paper-fetch -a cursor2Manually: put the files in place
.cursor/skills/paper-fetch/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install Agents365-ai/365-skills paper-fetch2Manually: put the files in place
.github/skills/paper-fetch/SKILL.md1Skills CLI (Vercel)
npx skills add Agents365-ai/365-skills --skill paper-fetch -a gemini-cli2Platform CLI
gemini skills install https://github.com/Agents365-ai/365-skills --path plugins/paper-fetch/skills/paper-fetchManually: put the files in place
.devin/skills/paper-fetch/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add Agents365-ai/365-skills --skill paper-fetch -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about paper-fetch
How do I install paper-fetch in Claude Code?
Run npx skills add Agents365-ai/365-skills --skill paper-fetch -a claude-code. The skill file is at ~/.claude/skills/paper-fetch/SKILL.md.
What does paper-fetch do?
It locates and downloads research paper PDFs from a DOI or title, and can process a file containing multiple DOIs.
Does paper-fetch need Python?
Yes. It requires python3. Publisher downloads also require institutional mode, enabled with PAPER_FETCH_INSTITUTIONAL=1.
